Interpretable Data-Driven Ship Dynamics Model: Enhancing Physics-Based Motion Prediction with Parameter Optimization

Abstract

The deployment of autonomous navigation systems on ships necessitates accurate motion prediction models tailored to individual vessels. Traditional physics-based models, while grounded in hydrodynamic principles, often fail to account for ship-specific behaviors in real-world conditions. Conversely, purely data-driven models offer specificity but lack interpretability and robustness in edge cases.

This study proposes a data-driven physics-based model that integrates physics-based equations with data-driven parameter optimization, leveraging the strengths of both approaches to ensure interpretability and adaptability. The model incorporates physics-based components such as 3-DoF dynamics, rudder, and propeller forces, while parameters such as resistance curve and rudder coefficients are optimized using synthetic data. By embedding domain knowledge into the parameter optimization process, the fitted model maintains physical consistency.

Validation of the approach is realized with two container ships by comparing, both qualitatively and quantitatively, predictions against ground-truth trajectories. The results demonstrate significant improvements in predictive accuracy and reliability of the data-driven physics-based models over baseline physics-based models tuned with traditional marine engineering practices. The fitted models capture ship-specific behaviors in diverse conditions, with their predictions being 51.6% (ship A) and 57.8% (ship B) more accurate, and 72.36% (ship A) and 89.67% (ship B) more consistent.

Why it matters

Accurate, vessel-specific motion prediction is a prerequisite for autonomous navigation — and for any decision system that needs to know what a ship will do next. This work shows that you do not have to choose between the interpretability of physics and the specificity of data: embedding parameter optimization inside a physics-based structure delivers both.